JMLR 2017 papers on Optimization
19 of the 147 papers published in JMLR 2017 (12.9%) are on Optimization, compared with 6.0% at JMLR 2016. They fall into 4 topics.
See JMLR 2017 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Nonconvex and smooth optimization · 10 papers
- An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback (151 citations)
- Second-Order Stochastic Optimization for Machine Learning in Linear Time (105 citations)
- Statistical and Computational Guarantees for the Baum-Welch Algorithm (51 citations)
- Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression (43 citations)
- Group Sparse Optimization via lp,q Regularization (37 citations)
- A Unified Formulation and Fast Accelerated Proximal Gradient Method for Classification (23 citations)
- Soft Margin Support Vector Classification as Buffered Probability Minimization (18 citations)
- SnapVX: A Network-Based Convex Optimization Solver (13 citations)
- Stabilized Sparse Online Learning for Sparse Data (11 citations)
- Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Optimizers · 4 papers
- Stochastic Gradient Descent as Approximate Bayesian Inference (489 citations)
- Probabilistic Line Searches for Stochastic Optimization (81 citations)
- Optimal Rates for Multi-pass Stochastic Gradient Methods (51 citations)
- On Perturbed Proximal Gradient Algorithms (2 citations)
Distributed and compressed · 3 papers
- Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement (54 citations)
- A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization (20 citations)
- A distributed block coordinate descent method for training l1 regularized linear classifiers
